Sensors, Vol. 20, Pages 4349: LdsConv: Learned Depthwise Separable Convolutions by Group Pruning

Sensors, Vol. 20, Pages 4349: LdsConv: Learned Depthwise Separable Convolutions by Group Pruning Sensors doi: 10.3390/s20154349 Authors: Wenxiang Lin Yan Ding Hua-Liang Wei Xinglin Pan Yutong Zhang Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation that is smart but has a strong capacity for learning. It integrates the pruning technique into the design of convolutional filters, formulated as a generic convolutional unit that can be used as a direct replacement of convolutions without any adjustments of the architecture. To show the effectiveness of the proposed method, experiments are carried out using the state-of-the-art convolutional neural networks (CNNs), including ResNet, DenseNet, SE-ResNet and MobileNet, respectively. The results show that by simply replacing the original convolution with LdsConv in these CNNs, it can achieve a significantly improved accuracy while reducing computational cost. For the case of ResNet50, the FLOPs can be reduced by 40.9%, meanwhile the accuracy on the associated ImageNet increases.
Source: Sensors - Category: Biotechnology Authors: Tags: Article Source Type: research